affinity-mcp@0.8.0
CAUTION· not startedPublisher claims: "Affinity MCP server" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Not started: dependency install failed; the server itself was not observed.- Tested
- the dependency install step · every file read, file written and host contacted by what ran
- Not tested
- server startup · the tool list · tool behavior
What this means for the label: Caution here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.
Before you give it your token
- It will ask for
- no credential variables read in the code
- Where it talks to
- no vendor host named in the codeAlso affinity.co, claude.ai — not the publisher's domain; check what for before connecting.
- What we saw when it ran
- no credential files read · no network
- What we could not test
- server startup · the tool list · tool behavior
Connect it under the guard. Not started: dependency install failed; the server itself was not observed. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
What changed since 0.6.0
vet-skills diff affinity-mcp 0.6.0 0.8.0In the sandbox, this version reached for nothing 0.6.0 did not. Compared from the two recorded runs, not from source.
- No longer contacted
- evil.com
0.6.0 was not run in the sandbox (install failed); the comparison covers what static analysis recorded only.
The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-22 and scored it 68/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Credential pass-through configuration; Access to sensitive file paths; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 1 s · 2 scenarios · 0 deviationsStatic findings
- OAuth2 access, impersonation, and happy-proxy tokens: RS256 JWTs — aFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.Settings are loaded from the env file specified by ENV_FILE (default: .env).Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.env_file=os.getenv("ENV_FILE", ".env"),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.CREDENTIAL_EXPIRED = "credential_expired" # our proxy token aged out mid-requestFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.prettier-ignoreFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.prettier-ignoreFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.prettier-ignoreFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.`[list_name]_import.csv`. Use `present_files` to hand the file and upload instructions to the userFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.prettier-ignoreFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.map after paths are surfaced. Always use this skill for warm intro questions — do not attempt toFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.- ``user_id`` and ``org_id`` — proxy tokens, from ``sub`` andFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.prettier-ignoreFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.Cost to the agent
Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.
Known vulnerabilities
Not checked against OSV yet; the weekly check has not reached this version.
What would make this Verified
12 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Text that tells the agent to ignore its instructions≈ +9 on the totalDelete phrases like "ignore previous instructions", "override", "bypass" from SKILL.md and tool descriptions. Describe what the skill does; do not instruct the agent about other rules.
- Unclaimed publisher≈ +8 on the totalClaim affinity-support: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
- Credential pass-through configuration≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.